> ## Documentation Index
> Fetch the complete documentation index at: https://social-b97141fb-auto-generate-llmstxt.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Sentiment Analysis

> AI-powered sentiment analysis that automatically detects topics, classifies sentiment, and generates actionable summaries from community conversations.

Sentiment Analysis uses AI to examine threads across your application, detect conversation topics, classify each mention as positive, neutral, or negative, and produce summaries with actionable recommendations — all without manual tagging or surveys.

## Features

<CardGroup cols={3}>
  <Card title="Sentiment Scoring" icon="face-smile">
    Overall sentiment score (0–100) with period-over-period comparison to track community health trends
  </Card>

  <Card title="Topic Detection" icon="hashtag">
    AI automatically identifies and tracks conversation topics across all analyzed threads
  </Card>

  <Card title="AI Summaries" icon="sparkles">
    Per-topic summaries of negative, neutral, and positive mentions with actionable recommendations
  </Card>

  <Card title="Thread-Level Analysis" icon="messages">
    Browse individual analyzed threads with detected topics and full conversation context
  </Card>

  <Card title="Trend Charts" icon="chart-line">
    Sentiment over time and mentions over time visualizations with percentage and absolute views
  </Card>

  <Card title="Settings" icon="gear">
    Define the custom topics the AI tracks, and re-run the current configuration over past threads with retroactive tagging
  </Card>
</CardGroup>

## Getting Started

| Requirement        | Details                                                                     |
| ------------------ | --------------------------------------------------------------------------- |
| Access             | Dashboard login with Moderator or Analyst permission                        |
| Feature enablement | Sentiment Analysis enabled on your network (contact support if not visible) |
| Credits            | Analysis uses thread credits — monitor usage in the credit banner           |
| Navigation         | **Dashboard → Social Insights → Sentiment analysis**                        |

<Info>
  Need Sentiment Analysis enabled? Email <a href="mailto:support@social.plus">[support@social.plus](mailto:support@social.plus)</a> with your network ID.
</Info>

## Credit & Analysis Coverage

At the top of the page a credit banner shows how many threads were analyzed out of your total credit allocation for the selected date range.

* **Coverage percentage** — A circular gauge (e.g., *95%*) indicates analysis completeness.
* **Thread count** — For example, *9520 of 10000 threads that matched the filters were analyzed*.
* **Manage credit** — Click to view or adjust your credit allocation.

<Warning>
  If the number of threads created or updated in your application exceeds your credit, not all threads will be analyzed by AI.
</Warning>

## Filtering & Date Range

### Date Range

Use the date picker in the top-right corner to select the analysis period. Comparison metrics (e.g., *+2 pts*, *+80%*) automatically reference the equivalent prior period.

### Filters

Click the **Filter** button to narrow analysis scope:

| Filter        | Description                                                    |
| ------------- | -------------------------------------------------------------- |
| **Community** | Filter by one or more communities using *Matches any of* logic |
| **User tag**  | Filter by user tags to focus on specific user segments         |

<Steps>
  <Step title="Open Filter Panel">
    Click the **Filter** button next to the date picker.
  </Step>

  <Step title="Select Filters">
    Choose communities and/or user tags from the dropdowns.
  </Step>

  <Step title="Apply">
    Click **Apply** to refresh all tabs with the filtered data. Use **Clear all** to reset.
  </Step>
</Steps>

## Overview Tab

The Overview tab provides a high-level snapshot of sentiment across your entire application (or filtered scope).

### Key Metrics

<CardGroup cols={3}>
  <Card title="Sentiment Score" icon="gauge">
    Score from 0–100 indicating overall community sentiment. Labeled **Positive**, **Neutral**, or **Negative**. Shows point change vs. the prior comparison period.
  </Card>

  <Card title="Total Topics Detected" icon="hashtag">
    Number of distinct topics the AI identified in the selected period. Shows percentage change vs. prior period.
  </Card>

  <Card title="Total Mentions" icon="comments">
    Aggregate count of all topic mentions across analyzed threads. Shows percentage change vs. prior period.
  </Card>
</CardGroup>

### Top Negative & Positive Topics

Two side-by-side panels highlight the topics with the highest concentration of negative and positive sentiment:

* **Top topic callout** — Shows the topic name, total mention count, and what percentage was negative or positive.
* **Horizontal bar chart** — Ranks the top 5 topics by total mentions. Negative chart bars are shown in red/orange; positive chart bars are shown in blue.

<Tip>
  Hover over any bar in the chart to see a breakdown of negative, neutral, and positive mention counts for that topic.
</Tip>

### Sentiment Breakdown

A donut chart showing the distribution of all mentions across three categories:

* **Negative mentions** (red) — count and percentage
* **Neutral mentions** (orange/yellow) — count and percentage
* **Positive mentions** (blue) — count and percentage

### Sentiment Over Time

A line chart tracking how sentiment proportions change over the selected date range. Toggle between:

* **Percentage** — Shows each sentiment category as a percentage of daily total
* **Number** — Shows absolute mention counts per day

## Topic Analysis Tab

The Topic Analysis tab provides a sortable table of all detected topics with detailed metrics.

| Column        | Description                                                                                                 |
| ------------- | ----------------------------------------------------------------------------------------------------------- |
| **Topic**     | Name of the detected topic                                                                                  |
| **Mentions**  | Total number of mentions (sortable)                                                                         |
| **Change**    | Percentage change vs. the prior comparison period (sortable). Shows *No baseline* for newly detected topics |
| **Sentiment** | Stacked horizontal bar showing negative %, neutral %, and positive %                                        |
| **Action**    | **View insights** link to drill into the topic detail page                                                  |

### Topic Detail Page

Clicking **View insights** on any topic opens a dedicated page with deep analysis for that specific topic.

<AccordionGroup>
  <Accordion title="KPI Cards" icon="chart-simple">
    * **Sentiment score** — Topic-specific score (0–100) with comparison to prior period
    * **Total mentions** — Mention count for this topic with percentage change
  </Accordion>

  <Accordion title="AI Summary Panel" icon="sparkles">
    The right-side panel provides AI-generated insights organized by sentiment:

    * **Negative mentions** — Summary of key negative themes with a **View threads** button to see source posts
    * **Neutral mentions** — Summary of neutral/mixed feedback
    * **Positive mentions** — Summary of positive themes and praise
    * **Recommendation** — Actionable suggestions derived from the analysis (e.g., *"Address concerns urgently. Consider user feedback surveys."*)
  </Accordion>

  <Accordion title="Mentions Over Time" icon="chart-line">
    Line chart showing how mention volume for this topic changed over the selected date range.
  </Accordion>

  <Accordion title="Sentiment Breakdown" icon="chart-pie">
    Donut chart showing negative, neutral, and positive distribution for this specific topic.
  </Accordion>

  <Accordion title="Sentiment Over Time" icon="chart-area">
    Line chart with **Percentage** and **Number** toggle showing sentiment trend for this topic.
  </Accordion>
</AccordionGroup>

## Analyzed Threads Tab

The Analyzed Threads tab lets you browse the actual posts and comments that were analyzed.

### Thread List (Left Panel)

A scrollable list of analyzed threads showing:

* **Author name** and avatar
* **Timestamp** (e.g., *2 Apr 2026, 17:35*)
* **Community name** where the thread was posted
* **Content preview** — Truncated text of the original post
* **Engagement** — Reaction count and comment count

### Thread Detail (Right Panel)

Selecting a thread displays:

* **Topic detected** — Tags showing which topics the AI identified in this thread (editable via tag icons)
* **Full post content** — Complete text including hashtags, mentions, and links
* **Engagement metrics** — Reactions and comments count
* **Comment thread** — All comments and replies with author, timestamp, and nested replies

<Tip>
  Use the Analyzed Threads tab to validate AI-generated summaries by reviewing the actual source posts that informed them.
</Tip>

## Settings

Access Settings via the **settings gear icon** (⚙) in the top-right corner of the Sentiment Analysis page. Settings has two tabs:

| Tab                     | Purpose                                                                        |
| ----------------------- | ------------------------------------------------------------------------------ |
| **Topic configuration** | Define the topics the AI tracks in new analyses                                |
| **Retroactive tagging** | Re-run the current topic configuration over threads that were already analyzed |

## Topic Configuration

<Info>
  This configuration applies to **new analyses only**. Changes take effect from the date they are saved, and previously completed analyses are not affected. To update past threads, use [Retroactive Tagging](#retroactive-tagging).
</Info>

### Managing Topics

<Steps>
  <Step title="Open Configuration">
    Click the settings gear icon on the Sentiment Analysis page to navigate to **Topic configuration**.
  </Step>

  <Step title="Review Existing Topics">
    View the table of configured topics with their names and date added. The table is sortable by **Date added**.
  </Step>

  <Step title="Add a Topic">
    Click **+ Add topic** to define a new topic for the AI to track in future analyses.
  </Step>

  <Step title="Remove a Topic">
    Click the delete icon (🗑) in the Action column to remove a topic from future analyses.
  </Step>
</Steps>

<Warning>
  Removing a topic stops future analysis for that topic but does not delete historical data. Historical results remain available for the date range when the topic was active.
</Warning>

## Retroactive Tagging

Topic configuration changes only apply going forward, so threads analyzed before a topic existed carry no mentions of it. Retroactive tagging closes that gap: it reprocesses historical threads in a date range you choose using the **current** topic configuration, then updates those threads with the new results.

Open it via **settings gear icon (⚙) → Retroactive tagging**.

<Info>
  Typical use: you add a topic today and want last month's conversations counted against it, or the AI missed an emerging theme you have since configured.
</Info>

### Job History

The tab lists every retroactive job for the network, newest first.

| Column             | Description                                                                   |
| ------------------ | ----------------------------------------------------------------------------- |
| **Date started**   | When the job was submitted                                                    |
| **Data range**     | The window that was reprocessed — threads published inside it are re-analyzed |
| **Topics applied** | The topic configuration snapshot used for the run (e.g., *30 topics*)         |
| **Threads found**  | Number of posts in the range that the job analyzed                            |
| **Status**         | **Processing**, **Completed**, or **Failed**                                  |
| **Action**         | **View details** opens the job's side panel                                   |

### Job Details

Click **View details** on any row to open a side panel containing:

* **Date range** as the panel title, with a note that historical threads in that range were reprocessed using the topic snapshot
* **Threads found** — the thread count for that job
* **Topic in this snapshot** — the exact topic list the run used, with each topic's *Date added*, sortable

Because the panel stores the snapshot, you can tell which topics existed at the time of a past run — useful when two jobs over the same range return different results.

### Running a Retroactive Job

<Steps>
  <Step title="Confirm Your Topics">
    On the **Topic configuration** tab, verify the topic list is what you want applied. The job uses the configuration as it exists at submission time.
  </Step>

  <Step title="Start the Flow">
    On the **Retroactive tagging** tab, click **+ Apply retroactively**.
  </Step>

  <Step title="Pick a Date Range">
    Choose the window to reprocess. Presets cover **Last 7 days**, **Last 14 days**, and **Last 30 days**; a two-month calendar handles custom ranges. Future dates are disabled, and preset ranges end on the previous day.
  </Step>

  <Step title="Review the Estimate">
    Click **Estimate**. The review step shows the data range with its day count, the number of topics being applied, the approximate **Threads found**, the **Credit required for this job**, and the **Credit remaining after** it runs.
  </Step>

  <Step title="Start the Job">
    Click **Start retroactive**. The job is queued and begins processing when capacity is available; affected threads are updated once it completes.
  </Step>
</Steps>

<Warning>
  **Retroactive jobs cannot be undone.** A running job can't be canceled, and a completed job can't be changed or deleted. Confirm the date range and credit cost on the review step before starting.
</Warning>

### Credit Cost

Retroactive jobs draw on the same thread credit pool as ongoing analysis — one credit per thread analyzed. **Threads found** on the review step is an estimate, and the review step is the only place the cost appears before the job starts.

## Daily Operational Workflow

<Steps>
  <Step title="Check Overview">
    Open Sentiment Analysis and review the three KPI cards for any significant changes in sentiment score, topic count, or mention volume.
  </Step>

  <Step title="Identify Problem Areas">
    Check the **Top negative topics** panel. If any topic shows a high negative percentage, click through to investigate.
  </Step>

  <Step title="Review AI Summaries">
    On the topic detail page, read the AI Summary panel's negative mentions and recommendations.
  </Step>

  <Step title="Validate with Source Data">
    Click **View threads** to review actual posts behind the AI summaries. Confirm findings before taking action.
  </Step>

  <Step title="Monitor Trends">
    Use the **Sentiment over time** chart to check whether negative sentiment is a spike or sustained trend.
  </Step>

  <Step title="Take Action">
    Convert high-confidence recommendations into backlog tickets, content changes, or moderation actions.
  </Step>
</Steps>

## Best Practices

<AccordionGroup>
  <Accordion title="Credit Management" icon="coins">
    * Monitor the credit banner regularly — if coverage drops below 80%, consider applying filters to prioritize high-value communities.
    * Use community and user tag filters to focus credits on segments that matter most.
    * Contact support to increase credit limits if your application consistently exceeds allocation.
  </Accordion>

  <Accordion title="Topic Configuration" icon="list-check">
    * Start with 5–10 broad topics and refine as patterns emerge from the AI analysis.
    * Review the Topic Analysis tab monthly to identify if any configured topics have zero mentions — consider replacing them.
    * Add new topics when you notice emerging themes in the Analyzed Threads tab.
    * Remember that topic changes only affect future analyses — use retroactive tagging to apply them to past threads.
  </Accordion>

  <Accordion title="Retroactive Tagging" icon="clock-rotate-left">
    * Finish adding topics before submitting a job — each run snapshots the configuration, so a forgotten topic means paying for the same range twice.
    * Start with a short range to measure credit cost per day, then widen it.
    * Check **Credit remaining after** on the review step; a wide range over a busy period can consume a large share of the pool.
    * Use each job's detail panel to compare topic snapshots when two runs over the same range disagree.
  </Accordion>

  <Accordion title="Interpreting Sentiment Scores" icon="scale-balanced">
    * A sentiment score of 50 indicates perfectly balanced sentiment — not necessarily good or bad.
    * Focus on **change over time** rather than absolute scores — a 5+ point drop warrants investigation.
    * Cross-reference sentiment shifts with product releases, incidents, or campaigns for causal analysis.
    * Low mention volumes can cause score volatility — set a minimum threshold before acting on changes.
  </Accordion>

  <Accordion title="Actionable Analysis" icon="bullseye">
    * Always validate AI summaries by reviewing source threads before escalating issues.
    * Use the **Recommendation** section as a starting point, not a final directive — apply business context.
    * Compare negative topics against positive topics to understand relative priority.
    * Track whether actions taken improve sentiment in subsequent analysis periods.
  </Accordion>
</AccordionGroup>

## Related Topics

<CardGroup cols={3}>
  <Card title="AI Research" icon="magnifying-glass" href="./social-insights">
    Ad-hoc natural language analysis across community conversations
  </Card>

  <Card title="Social Analytics" icon="chart-bar" href="./social-analytics">
    Quantitative engagement and usage metrics for social features
  </Card>

  <Card title="Raw Data Export" icon="download" href="./raw-data-export">
    Export raw data for deeper custom analysis and reporting
  </Card>
</CardGroup>